Quasi-Experimental Methods

for Environmental & Resource Economists

Corbett Grainger

Agricultural & Applied Economics

University of Wisconsin

corbett.grainger@wisc.edu

Goals/Overview

This course will provide an overview of modern “quasi-experimental” methods for environmental and resource economists.

In contrast to experimental settings, observational data are used in most empirical studies in environmental and natural resource economics. Observational data are not generated in a controlled experimental setting, so understanding the relationships between variables requires advanced statistical tools. Applied econometricians have developed an array of methods for causal inference using observational data. These tools are particularly well-suited for analyzing the effects of policy interventions, which is often of interest to environmental economists.

The course will cover a range of topics in applied econometrics, including difference-in-differences, event studies using panel data, instrumental variables, regression discontinuity design, and matching. Each topic will be introduced analytically, but the focus will be on recent implementations of these tools in environmental and resource economics.

Participants will come away with an understanding of the tool-kits available to applied researchers, including when different approaches may be used, the assumptions required for validity, and examples from recent research papers.

Topics:

1) Cross Section

a. Review assumptions for identification (Cunningham pg 35-104)

b. Matching (Cunningham pg 105)

Example: Fowlie et al (2012)

c. Regression Discontinuity (Cunningham pg 153)

Example: Boomhower (2019)

d. Instrumental Variables (Cunningham pg 205)

Example: Grainger (2012)

2) Panel Data

a. Difference-in-Differences (Cunningham pg 263)

Example: Evans (2016)

b. Event Study (generalized diff-in-diff)

Example: Costello and Grainger (2018)

c. Propensity Score Matching

Costello et al (2008)

d. Synthetic Control (Cunningham pg 287)

Example: Abadie et al (2010)

e. IV in a panel (time varying instrument)

Costello and Grainger (2018)

References

  • Angrist, J.D. and Pischke, J.S., 2008. Mostly harmless econometrics: An empiricist's companion. Princeton university press.
  • Boomhower, J., 2019. Drilling like there's no tomorrow: Bankruptcy, insurance, and environmental risk. American Economic Review, 109(2), pp.391-426.
  • Costello, C., Gaines, S.D. and Lynham, J., 2008. Can catch shares prevent fisheries collapse?. Science, 321(5896), pp.1678-1681.
  • Costello, C. and Grainger, C.A., 2018. Property rights, regulatory capture, and exploitation of natural resources. Journal of the Association of Environmental and Resource Economists, 5(2), p.441-479.
  • Cunningham, Scott. 2018. Causal Inference: The Mixtape (V 1.7).
  • Evans, M. (2016). The Clean Air Act watch list: an enforcement and compliance natural experiment. Journal of the Association of Environmental and Resource Economists 3: 627-665.
  • Fowlie, M., Holland, S.P. and Mansur, E.T., 2012. What do emissions markets deliver and to whom? Evidence from Southern California's NOx trading program. American Economic Review, 102(2), pp.965-93.